Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2590 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5202. Min Range: -7.5202
Max Act: 7.5202. Min Act: -0.1700
Data Index: 501287 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5202. Min Range: -7.5202
Max Act: 7.0827. Min Act: -0.1700
Data Index: 375196 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5202. Min Range: -7.5202
Max Act: 7.0514. Min Act: -0.1700
Data Index: 604182 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5202. Min Range: -7.5202
Max Act: 6.9889. Min Act: -0.1700
Data Index: 1348187 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5202. Min Range: -7.5202
Max Act: 6.9577. Min Act: -0.1700
Data Index: 1574127 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5202. Min Range: -7.5202
Max Act: 6.9264. Min Act: -0.1700
Data Index: 5567226 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5202. Min Range: -7.5202
Max Act: 6.9264. Min Act: -0.1700
Data Index: 4198568 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5202. Min Range: -7.5202
Max Act: 6.8952. Min Act: -0.1700
Data Index: 7736480 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5202. Min Range: -7.5202
Max Act: 6.8952. Min Act: -0.1700
Data Index: 7398291 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5202. Min Range: -7.5202
Max Act: 6.8327. Min Act: -0.1700
Data Index: 7952128 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5202. Min Range: -7.5202
Max Act: 6.8639. Min Act: -0.1700
Data Index: 911978 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5202. Min Range: -7.5202
Max Act: 6.7702. Min Act: -0.1700
Data Index: 946753 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5202. Min Range: -7.5202
Max Act: 6.7702. Min Act: -0.1700
Data Index: 4566899 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5202. Min Range: -7.5202
Max Act: 6.7702. Min Act: -0.1700
Data Index: 853495 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5202. Min Range: -7.5202
Max Act: 6.7389. Min Act: -0.1700
Data Index: 3973489 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5202. Min Range: -7.5202
Max Act: 6.7077. Min Act: -0.1700
Data Index: 5053991 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5202. Min Range: -7.5202
Max Act: 6.6452. Min Act: -0.1700
Data Index: 5474330 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5202. Min Range: -7.5202
Max Act: 6.5827. Min Act: -0.1700
Data Index: 4203591 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5202. Min Range: -7.5202
Max Act: 6.6139. Min Act: -0.1700
Data Index: 304073 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5202. Min Range: -7.5202
Max Act: 6.5827. Min Act: -0.1700
Data Index: 6094995 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19